Update to add Cuda to build system

kernels/hello_world.cu

@@ -0,0 +1,46 @@
+#include <cuda_runtime.h>
+#include <stdio.h>
+
+__global__ void hello_cuda() {
+  printf("Hello CUDA from thread %d\n", threadIdx.x);
+}
+
+extern "C" void launch_hello_cuda() {
+  // First check device properties
+  cudaDeviceProp prop;
+  cudaGetDeviceProperties(&prop, 1);
+  printf("Using device: %s with compute capability %d.%d\n", prop.name,
+         prop.major, prop.minor);
+
+  hello_cuda<<<1, 10>>>();
+  cudaDeviceSynchronize();
+  fflush(stdout);
+}
+
+extern "C" void check_cuda() {
+  int deviceCount = 0;
+  cudaError_t error = cudaGetDeviceCount(&deviceCount);
+
+  if (error != cudaSuccess) {
+    printf("CUDA error: %s\n", cudaGetErrorString(error));
+  }
+
+  printf("Found %d CUDA devices\n", deviceCount);
+
+  for (int i = 0; i < deviceCount; i++) {
+    cudaDeviceProp prop;
+    cudaGetDeviceProperties(&prop, i);
+
+    printf("Device %d: %s\n", i, prop.name);
+    printf("  Compute capability: %d.%d\n", prop.major, prop.minor);
+    printf("  Total global memory: %.2f GB\n",
+           static_cast<float>(prop.totalGlobalMem) / (1024 * 1024 * 1024));
+    printf("  Multiprocessors: %d\n", prop.multiProcessorCount);
+    printf("  Max threads per block: %d\n", prop.maxThreadsPerBlock);
+    printf("  Max threads dimensions: (%d, %d, %d)\n", prop.maxThreadsDim[0],
+           prop.maxThreadsDim[1], prop.maxThreadsDim[2]);
+    printf("  Max grid dimensions: (%d, %d, %d)\n", prop.maxGridSize[0],
+           prop.maxGridSize[1], prop.maxGridSize[2]);
+    printf("\n");
+  }
+}